Current Research Activity
Indranil Ghosh and Tamal Datta Chaudhuri, “Understanding and Forecasting Stock Market Volatility through Wavelet Decomposition, Statistical Learning and Econometric Methods”, 4th International Conference in Business Analytics and Intelligence (ICBAI-2016), Held at IISC Bangalore, December 19-21, 2016.
Volatility in stock markets evokes varying responses from market participants. While some perceive it as opportunity to make money, others perceive it as a threat and start unwinding their positions. In today’s globalized environment, increased volatility reflects not only the domestic macroeconomic state, but also global uncertainty. While volatility in the stock market as a whole can be influenced by events like oil price shocks, increase in rates of interest in the US and domestic elections, volatility in individual stock prices can be due to perceived growth prospects of the company or the sector, company specific news or policy announcements that can affect a company/sector. In this study, associations, causal influence among three volatility indicators namely, CBOE VIX, INDIA VIX and Historic Volatility (HV) have been carefully examined, and predictive models for forecasting have been developed. An integrated framework incorporating Wavelet decomposition, statistical predictive modeling and standard econometric methods is presented to accomplish the research objectives.
Jaydip Sen and Tamal Datta Chaudhuri, “Decomposition of Time Series Data to Check Consistency between Fund Style and Actual Fund Composition of Mutual Funds”, 4th International Conference in Business Analytics and Intelligence (ICBAI-2016), Held at IISC Bangalore, December 19-21, 2016.
We propose a novel approach for analysis of the composition of an equity mutual fund based on the time series decomposition of the price movements of the individual stocks of the fund. The proposed scheme can be applied to check whether the style proclaimed for a mutual fund actually matches with the fund composition. We have applied our proposed framework on eight well known mutual funds of varying styles in the Indian financial market to check the consistency between their fund style and actual fund composition, and have obtained extensive results from our experiments. A detailed analysis of the results has shown that while in majority of the cases the actual allocations of funds are consistent with the corresponding fund styles, there have been some notable deviations too.
Tamal Datta Chaudhuri, Indranil Ghosh and ShahiraEram, “Application of Unsupervised Feature Selection, Machine Learning and Evolutionary Algorithm in Predicting Stock Returns – A Study of Indian Firms (2016)”, IUP Journal of Financial Risk Management, Vol. 13, Issue 3, pp. 20-47.
Prediction of stock prices has become an important area of research in the field of financial analyticsand has garnered a lot of attention among academicians. Drawing on the literature on application of econometric tools and also machine learning techniques, this paper presents a framework for predicting stock returns using three unsupervised feature selection techniques, four predictivemodeling techniques and finally an ensemble combining the four predictive modeling techniques. To design the ensemble, evolutionary algorithm is applied. In order to assess the results of our study, four different performance measures, namely, Mean Absolute Error (MAE), Mean Squared Error (MSE), Nash-Sutcliffe Efficiency (NSE) and Index of Agreement (IA) have been utilized. Our feature selection results indicate that all explanatory variables are not significant for different classes of companies and also for different time periods. This gives us insight into the fact that, for stock returns prediction, one has to be careful of the predictors to be chosen. Further, results indicate that for all the forecasting methods, namely, random forest, bagging, boosting and support vector regression, forecasting efficiency for large cap and mid-cap firms was better than that of small cap firms. Statistical analysis through Analysis of Variance (ANOVA) suggests that of all four predictive modeling techniques, boosting was the most efficient technique for forecasting the stock returns. We then proceeded to construct an ensemble of the above four methods. In terms of all four measurement metrics, performance of the proposed ensemble was better in both training and testing phase as compared to the efficiency of the individual predictive modeling techniques.
Tamal Datta Chaudhuri, Indranil Ghosh and Priym Singh, “Application of Machine Learning Tools in Predictive Modeling of Pairs Trade in Indian Stock Market”, Accepted for publication in IUP Journal of Applied Finance (January Issue, 2017).
The paper applies machine learning tools in pairs trading. Three different algorithms namely Support Vector Machine (SVM), Random Forest (RF) and Adaptive Neuro Fuzzy Inference System (ANFIS) have been used for predictive modeling of the value of the ratio of share prices of pairs of companies. The study considers nine different independent variables/features for forecasting. The analytical framework combines the mean reverting property of the movement of a pair of prices along with technical indicators. We also use Feature Selection Algorithms for justification of the nine independent variables. The results support our methodology and also selection of the features for prediction.